AI Agentic Scraping Engineer

Role overview Build and maintain data extractors that turn product listings and detail pages across online shops into consistent, structured records for use by AI agents. You will use AI coding agents to draft, test, and repair these extractors, while remaining responsible for data accuracy and the reliability of the extraction workflows.

Responsibilities - Create and maintain extractors for marketplace, retailer, and brand search, catalog, and product pages. - Design agent workflows that generate extractors, test them against live pages, and prepare reviewable pull requests. - Monitor sources for changes using schema checks, sample runs, and alerts, then repair extraction issues. - Normalize prices, currencies, variants, availability, and seller information into a consistent record format. - Coordinate with backend engineers on job reliability, retry behavior, and per-page costs.

Requirements - Three or more years of production experience collecting website data at scale with Python or TypeScript. - Regular hands-on use of AI coding agents and practical judgment about their limitations. - Familiarity with HTTP, HTML, embedded JSON APIs, and browser automation. - Habit of testing and validating data as well as code. - Clear written English for pull requests, issues, and incident notes.

Nice to have - Experience working with ecommerce data from marketplaces, retailers, or platforms such as Amazon or Shopify. - Experience building or using MCP servers or LLM tool calling. - Background in product matching or entity resolution.